Epoch: 0001 train_loss= 1.38867 train_acc= 0.32542 val_loss= 1.40667 val_acc= 0.33929 time= 0.31252
Epoch: 0002 train_loss= 1.37882 train_acc= 0.32263 val_loss= 1.40004 val_acc= 0.33929 time= 0.01563
Epoch: 0003 train_loss= 1.38222 train_acc= 0.29749 val_loss= 1.39467 val_acc= 0.33929 time= 0.01563
Epoch: 0004 train_loss= 1.38077 train_acc= 0.31844 val_loss= 1.39087 val_acc= 0.33929 time= 0.01563
Epoch: 0005 train_loss= 1.38341 train_acc= 0.30587 val_loss= 1.38840 val_acc= 0.33929 time= 0.01563
Epoch: 0006 train_loss= 1.37839 train_acc= 0.31983 val_loss= 1.38728 val_acc= 0.33929 time= 0.01563
Epoch: 0007 train_loss= 1.37615 train_acc= 0.31983 val_loss= 1.38753 val_acc= 0.33929 time= 0.01563
Epoch: 0008 train_loss= 1.37225 train_acc= 0.31983 val_loss= 1.38838 val_acc= 0.33929 time= 0.01563
Epoch: 0009 train_loss= 1.37748 train_acc= 0.31983 val_loss= 1.38962 val_acc= 0.33929 time= 0.01563
Epoch: 0010 train_loss= 1.36978 train_acc= 0.32682 val_loss= 1.39068 val_acc= 0.33929 time= 0.03125
Epoch: 0011 train_loss= 1.37368 train_acc= 0.32402 val_loss= 1.39123 val_acc= 0.33929 time= 0.01562
Epoch: 0012 train_loss= 1.37238 train_acc= 0.32123 val_loss= 1.39177 val_acc= 0.33929 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.39734 accuracy= 0.28319 time= 0.00000 
